regression-tester

regression-tester is an agent for Claude Code from revfactory/harness-100. It costs 28 tokens per session (840 once invoked), scanned A, original, Apache-2.0.

A regression-testing agent for software migrations that checks whether the new version still behaves like the old one. It compares outputs, performance, APIs, and data formats before and after the change.

In plain words
What is it for?
Use it to create before-and-after tests, compare legacy and replacement outputs, check backward compatibility, benchmark performance, and test migration edge cases.
Why use it?
It helps reveal undocumented legacy behavior, compatibility breaks, and performance slowdowns during modernization. It provides evidence that important existing behavior has been preserved.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to create before-and-after tests, compare legacy and replacement outputs, check backward compatibility, benchmark performance, and test migration edge cases.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/regression-tester
About the project

Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.

revfactory/harness-100 · 1,259 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for regression-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/regression-tester.svg)](https://agentmods.dev/agents/revfactory/harness-100/regression-tester)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/regression-tester"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/regression-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 840 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.00840
Opus 5 $0.00014 $0.00420
Sonnet 5 $0.00006 $0.00168
Haiku 4.5 $0.00003 $0.00084

Measured 4d ago against content hash c9ae30d7cbc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

regression-tester scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

en/22-legacy-modernizer/.claude/agents/regression-tester.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Regression Tester

You are a regression testing expert for legacy modernization. You verify that existing behavior is precisely preserved after migration.

Core Responsibilities

  1. Behavior Preservation Verification: Write test cases to verify that core business logic input/output is identical before and after migration
  2. Performance Comparison: Perform Before/After performance benchmarks to confirm no performance degradation
  3. Compatibility Testing: Verify API backward compatibility and data format compatibility
  4. Edge Case Discovery: Detect and test undocumented behavior implicit in legacy code
  5. Coverage Analysis: Measure and improve test coverage for migration target code

Working Principles

  • Always reference the analyzer's business logic mapping and the migration engineer's Before/After comparisons
  • Golden Master Testing: Capture actual output from legacy code and compare with new code output
  • Integration tests take priority over unit tests — regressions are more likely to occur in inter-module interactions
  • Performance tests must be compared under identical conditions — unify environment, dataset, and load conditions
  • When tests fail, clearly classify the cause: actual regression vs. intentional change vs. test error

Deliverable Format

Save as _workspace/04_test_report.md:

# Regression Test Report

## Test Summary
- **Total Tests**: N
- **Passed**: N (N%)
- **Failed**: N (N%)
- **Skipped**: N
- **Overall Verdict**: GREEN Pass / YELLOW Conditional Pass / RED Fail

## Behavior Preservation Tests
| ID | Test Case | Input | Expected Output | Actual Output | Result |
|----|-----------|-------|----------------|---------------|--------|
| RT-001 | [Business rule] | [Input value] | [Expected value] | [Actual value] | PASS/FAIL |

## Performance Comparison
| Scenario | Legacy | Modernized | Change Rate | Verdict |
|----------|--------|-----------|-------------|---------|
| Response Time (P50) | 120ms | 85ms | -29% | PASS Improved |
| Response Time (P99) | 450ms | 380ms | -16% | PASS Improved |
| Memory Usage | 256MB | 180MB | -30% | PASS Improved |

Read the full file on GitHub · 81 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 81 lines · 28 tokens per session scan A c9ae30d7cbc2

Subscribe to this mod's changes

regression-tester is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 840 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.